TensorRTFlags enum
A flag for OrtProvider.tensorrt. TensorRT provides optimized inference on NVIDIA GPUs with additional optimizations.
Values
- useNone → const TensorRTFlags
-
Use default TensorRT provider options
const TensorRTFlags(0x000) - useFp16 → const TensorRTFlags
-
Enable TensorRT FP16 (half precision) mode Faster inference with minimal accuracy loss
const TensorRTFlags(0x001) - useInt8 → const TensorRTFlags
-
Enable TensorRT INT8 quantization Even faster with calibration, more accuracy loss
const TensorRTFlags(0x002) - forceSequentialEngineBuild → const TensorRTFlags
-
Force sequential engine building More stable but slower model initialization
const TensorRTFlags(0x004)
Properties
- hashCode → int
-
The hash code for this object.
no setterinherited
- index → int
-
A numeric identifier for the enumerated value.
no setterinherited
- name → String
-
Available on Enum, provided by the EnumName extension
The name of the enum value.no setter - runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
- value → int
-
no setteroverride
Methods
-
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a nonexistent method or property is accessed.
inherited
-
toString(
) → String -
A string representation of this object.
inherited
Operators
-
operator ==(
Object other) → bool -
The equality operator.
inherited
Constants
-
values
→ const List<
TensorRTFlags> - A constant List of the values in this enum, in order of their declaration.